Instructions for online reading groups can be found here.

Zoom link for all online reading groups:

Understanding Vision Transformers
Presented by Klara Janouskova

Gradient based sample selection for online continual learning
Presented by Ai Jianhang

EditGAN:High-precision semantic image editing
Presented by Adela Subrtova

Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
Presented by Vladan Stojnic

NeRF in detail: Learning to sample for view synthesis
Presented by Diana Sungatullina

OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning
Presented by Zdeněk Rozsypálek

UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction
Presented by Varun Burde

Past presentations

Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task, CVPR 2020
Presented by Arash Amjadi, slides

Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly, PAMI 2018
Presented by Pavel Suma, slides

Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision, 3DV 2021
Presented by Afzal Ahmad, slides

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, NAACL-HLT 2019
Presented by Ondrej Kobza, slides

Self-supervised video object segmentation by motion grouping, ICCV 2021
Presented by Juliette Bertrand, slides

Decision Transformer: Reinforcement Learning via Sequence Modeling, NeurIPS 2021
Presented by Aurele HAINAUT, slides

Pixel-Perfect Structure-from-Motion with Featuremetric Refinement, ICCV 2021
Presented by Pietrantoni Maxime, slides

Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains, NeurIPS 2020
Presented by Shubhan Patni, slides

NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis,, ECCV 2020
Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields, ICCV 2021
Presented by Jonas Kulhanek , slides

Convolutional Occupancy Networks, ECCV 2020
Presented by Jan Kúdelka , slides

Visformer: The Vision-Friendly Transformer, ICCV 2021
Presented by Nikita Sokovnin , slides

Online Class-Incremental Continual Learning with Adversarial Shapley Value, AAAI 2021
Presented by Arti Bandhana

26/10/21  End-to-End Object Detection with Transformers, ECCV 2020
Presented by Volodymyr Zabulskyi
21/10/21  Fast end-to-end learning on protein surfaces, CVPR 2021
Presented by Petr Kouba
14/10/21  Deep semi-supervised learning with consistency loss
Material: [1] [2] [3 ]
Presented by Awet Haileslassie Gebrehiwot, slides,
29/07/21  Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich Tasks
Michelle A. Lee , Yuke Zhu, Peter Zachares, Matthew Tan, Krishnan Srinivasan, Silvio Savarese, Li Fei-Fei, Animesh Garg , and Jeannette Bohg, IEEE TRANSACTIONS ON ROBOTICS, 2020
Presented by Louis Montaut, slides,
22/04/21  Domain-Adversarial Training of Neural Networks
Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M. and Lempitsky, V., JMLR 2016
Presented by Nikos Efthymiadis, slides,
02/03/21  Transporter Networks: Rearranging the Visual World for Robotic Manipulation
Andy Zeng, Pete Florence, Jonathan Tompson, Stefan Welker, Jonathan Chien, Maria Attarian, Travis Armstrong, Ivan Krasin, Dan Duong, Vikas Sindhwani, Johnny Lee, CoRL 2020
Presented by Kateryna Zorina , slides
25/02/21  Class-Balanced Loss Based on Effective Number of Samples
Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang Song, Serge Belongie, CVPR 2019
Presented by Kang Cheng , slides
12/01/21  Support-set bottlenecks for video-text representation learning, Mandela Patrick, Po-Yao Huang, Yuki Asano, Florian Metze, Alexander Hauptmann, João Henriques, Andrea Vedaldi, ICLR 2021
Presented by Tomas Soucek, slides
15/12/20  SuperGlue: Learning Feature Matching with Graph Neural Networks
Paul-Edouard Sarlin, Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich, CVPR 2020
Presented by Ilia Shipachev, slides
10/12/20  Contrastive learning for visual representations - Part 2
Material: [1] [2]
Presented by Antonin Vobecky, slides
08/12/20  Contrastive learning for visual representations - Part 1
Material: [1] [2]
Presented by Patrik Vacek, slides
01/12/20 DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization
Juan Du, Rui Wang, Daniel Cremers, ECCV 2020
Presented by Vojtěch Pánek, slides
26/11/20 Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval
Andrew Brown, Weidi Xie, Vicky Kalogeiton, Andrew Zisserman. ECCV 2020
Presented by Yash Patel, slides
23/10/20 Multi-Instance Classification by Max-Margin Training of Cardinality-Based Markov Networks
Hossein Hajimirsadeghi and Greg Mori. PAMI 2017
Presented by Dennis Baručić, slides
13/10/20 High-Frequency Component Helps Explain the Generalization of Convolutional Neural_Networks
Haohan Wang, Xindi Wu, Zeyi Huang, Eric P. Xing. CVPR 2020
Presented by Filip Naiser, slides
9/09/20 PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
Deqing Sun, Xiaodong Yang, Ming-Yu Liu, and Jan Kautz. CVPR 2018
Presented by Michal Neoral, slides
11/06/20 Deep Hough Voting for 3D Object Detection in Point Clouds
Charles Qi, Or Litany, Kaiming He, Leonidas J. Guibas. ICCV 2019
Presented Jan Bayer, slides
14/05/20  Variational Autoencoders with application to unsupervised representation learning
Material: main paper, VAE background, optional1, optional2
Presented by Yash Patel, slides
14/04/20  node2vec: Scalable feature learning for networks
A. Grover, J. Leskovec. ACM SIGKDD 2016
Presented by Tomáš Nováček, slides
12/03/20 GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
David Bau, Jun-Yan Zhu, Hendrik Strobelt, Bolei Zhou, Joshua B. Tenenbaum, William T. Freeman, Antonio Torralba. ICLR 2019
Presented by Jakub Žitný, slides
14/01/20 Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
Arslan Chaudhry, Puneet K. Dokania, Thalaiyasingam Ajanthan, Philip H. S. Torr, ECCV 2018.
Presented by Miloš Prágr, slides
09/01/20 LOGAN: Latent Optimisation for Generative Adversarial Networks
Yan Wu, Jeff Donahue, David Balduzzi, Karen Simonyan, Timothy Lillicrap
Presented by Michal Šustr, slides
21/11/19 ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
R. Geirhos, P. Rubisch, C. Michaelis, M. Bethge, F. Wichmann, W. Brendel, ICLR 2019
Presented by Nikos Efthymiadis, slides
05/11/19 Event-Based Motion Segmentation by Motion Compensation
T. Stoffregen, G. Gallego, T. Drummond,L. Kleeman, D. Scaramuzza. ICCV 2019
Presented by Holesovsky Ondrej, slides
12/09/19 The Inverted Multi-Index
A. Babenko and V. Lempitsky, PAMI 2014
Presented by Denis Efremov, slides
05/09/19 Video Propagation Networks
V. Jampani, R. Gadde and P. Gehler, CVPR 2017
Presented by Jonas Serych, slides
30/08/19 A General Solver Based on Sparse Resultants
I. Emiris, PoSSo 1995,
Presented by Pavel Trutman, slides
26/3/19 Dynamic Graph CNN for Learning on Point Clouds
Y. Wang, Y. Sun, Z. Liu, S. Sarma, M. Bronstein, J. Solomon, arxiv 2018,
Presented by Otakar Jašek, slides
17/1/19 Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
C. Finn, P. Abbeel, S. Levine, ICML 2017,
Presented by Teymur Azayev, slides
20/11/18 Semi-supervised classification with graph convolutional networks
T. Kipf and M. Welling, ICLR 2017,
Presented by Radim Špetlík, slides
24/05/18 Fast edge detection using structured forests
P. Dollar and L. Zitnick, PAMI 2015,
Presented by Vojtěch Cvrček, slides
24/04/18 Compressed Sensing
David L. Donoho, IEEE Transacations on Information Theory, 2006
Presented by Rickard Hole Falck
27/03/18 Dynamic Routing Between Capsules
S. Sabour, N. Frosst, G. Hinton, NIPS 2017
Presented by Karel Ha, slides.
14/12/17 Deformable Convolutional Networks
J. Dai, H. Qi, Y. Xiong, Y. Li,. Zhang, H. Hu, Y. Wei, ICCV 2017
Presented by Tomáš Jeníček, slides.